@uipath/skills 1.202.0-preview.755 → 1.202.0-preview.767

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@uipath/skills",
-  "version": "1.202.0-preview.755",
+  "version": "1.202.0-preview.767",
   "description": "UiPath agent skills for Claude Code, Codex, Cursor, Copilot, Gemini and OpenCode — RPA, UI automation, UI testing, coded agents/apps/workflows, and troubleshooting. Distributed as the UiPath Claude Code plugin.",
   "author": {
     "name": "UiPath"

package/skills/uipath-agents/references/lowcode/agent-definition.md

@@ -235,7 +235,7 @@ For **conversational agents**, each agent run handles one conversational exchang
 
 For **autonomous agents**, the `outputSchema` defines the output properties of the agent.
 
-For **conversational agents**, the `outputSchema` should not be modified, and thus always left empty. See [critical-rules/conversational-critical-rules.md](critical-rules/conversational-critical-rules.md) anti-pattern 1.
+For **conversational agents**, the `outputSchema` should not be modified, and thus always left empty. The exception is a conversational agent scaffolded inline in a Maestro Flow, which does support structured outputs and is authored under the `uipath-maestro-flow` skill. See [critical-rules/conversational-critical-rules.md](critical-rules/conversational-critical-rules.md) anti-pattern 1.
 
 
 ## Messages

package/skills/uipath-agents/references/lowcode/critical-rules/conversational-critical-rules.md

@@ -8,7 +8,9 @@ These rules are the canonical source for rules specific to low-code conversation
 
 ## What NOT to Do
 
-1. **Do not add properties to the `outputSchema` of a conversational agent.** After initialization, leave `outputSchema` empty. The conversational agent runtime streams responses/tool-call events during the execution, so the final output is not relevant for the end-user in the conversation.
+1. **Do not add properties to the `outputSchema` of a conversational agent built here.** After initialization, leave `outputSchema` empty. Standalone, in-solution and published conversational agents do not support structured outputs — the runtime streams responses/tool-call events during the execution, so the final output is not relevant for the end-user in the conversation, and a populated schema is never filled.
+
+   **The exception is a conversational agent scaffolded inline in a Maestro Flow** (a `uipath.agent.conversational` node), authored under the `uipath-maestro-flow` skill. These inline conversational agent nodes allow structured outputs for branching capabilities, such as handing the conversation between several single-prompt conversational agent nodes.
 
 2. **Do not author any `builtInValidator` guardrail on a conversational agent, and do not set `selector.scopes` to anything other than `["Tool"]`.** Built-in validators (any `$guardrailType: "builtInValidator"`) are autonomous-only; Agent- and Llm-scoped guardrails are likewise not honored. Author the Custom `Tool` guardrail at the `agent.json` root `guardrails[]` (authoritative for UI + runtime) and mirror it into the tool's `resources/<Tool>/resource.json` → `guardrail.policies[]`; a guardrail only in the tool resource is invisible in Studio Web and does not run on the Unified (Python) runtime, per Critical Rule 1.
 

package/skills/uipath-agents/references/lowcode/lowcode.md

@@ -22,14 +22,13 @@ UiPath low-code agents come in **two variants**, both sharing this skill.
    
 2. Conversational agents are intended for use-cases involving multi-turn conversations / fast latency with real-time user-interaction / streamed responses.
 
-> Currently, conversational agents are only standalone and not yet supported to be inline in a flow, so inline-in-flow use-cases should always use an autonomous agent.
 > After deployment, conversational agents are interacted with through the UiPath Conversation Service, which manages conversation history and exposes a CLI/SDK for client UIs. Each user-initiated exchange invokes the agent for a single turn, streaming events back to the client.
+> A standalone conversational agent is the simplest way to build a back-and-forth chat assistant driven by a single system prompt. For chats that need more — routing between several agents, deterministic replies, or behind-the-scenes automations running while the conversation continues — direct the user to the `uipath-maestro-flow` skill.
 
 In summary:
 | Signal | Variant |
 |---|---|
 | User wants general input → output execution | **Autonomous** |
-| User wants inline-in-flow | **Autonomous** |
 | `agent.json` has `metadata.isConversational: false` or unset | **Autonomous** |
 | User wants multi-turn chat / fast latency with real-time user-interaction / streamed responses | **Conversational** |
 | Existing `agent.json` has `metadata.isConversational: true` | **Conversational** |

package/skills/uipath-agents/references/lowcode/project-lifecycle.md

@@ -30,7 +30,7 @@ The `<path>` argument is relative or absolute; the command can run from any dire
 - `--model <model>` — LLM model to use (default: `gpt-5.4` for autonomous, `anthropic.claude-sonnet-4-5-20250929-v1:0` for conversational). This default is stale; override it post-init — discover current tenant models with `uip agent model list` and select per [model-selection-guide.md](model-selection-guide.md). Pass `--model` at init or edit `settings.model` after.
 - `--system-prompt <prompt>` — Initial system prompt for the agent
 - `--force` — Overwrite existing directory if non-empty
-- `--inline-in-flow` — Scaffold an inline agent inside a flow project (see below). Only applicable for autonomous agents, since adding inline conversational-agents within a flow project is currently not an enabled feature.
+- `--inline-in-flow` — Scaffold an inline agent inside a flow project (see below).
 
 #### Inline mode: `--inline-in-flow`
 
@@ -45,7 +45,7 @@ uip agent init "<FLOW_PROJECT_DIR>" --inline-in-flow --output json
 { "Result": "Success", "Code": "LowCodeAgentInitInline", "Data": { "Status": "Inline agent created inside flow project", "Path": "/path/to/FlowProject/<uuid>", "ProjectId": "<uuid>", "Model": "gpt-4o-2024-11-20" } }
 ```
 
-After scaffolding, add a `uipath.agent.autonomous` node to the flow with `inputs.source = <ProjectId>` and no node instance `model` block. See [capabilities/inline-in-flow/inline-in-flow.md](capabilities/inline-in-flow/inline-in-flow.md) for the full structure.
+After scaffolding an autonomous agent, add a `uipath.agent.autonomous` node to the flow with `inputs.source = <ProjectId>` and no node instance `model` block. See [capabilities/inline-in-flow/inline-in-flow.md](capabilities/inline-in-flow/inline-in-flow.md) for the full structure. Inline conversational agents are added with a `uipath.agent.conversational` node and are authored under the `uipath-maestro-flow` skill.
 
 ### `uip agent guardrails list`
 

package/skills/uipath-agents/references/lowcode/prompting/conversational-agent-prompting-guide.md

@@ -103,7 +103,7 @@ User message: `""` — left blank. The Conversational Service injects the user t
 | Field | Default | Change when |
 |-------|---------|-------------|
 | `inputSchema` | `{ "properties": {} }` | Add fields only when per-exchange, variable-based context beyond conversation history is genuinely needed. Reserved names: `messages`, `uipath__*` ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-patterns 4 and 5). |
-| `outputSchema` | `{ "type": "object", "properties": {} }` | **Never populate** — runtime streams events, does not fill output ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-pattern 1). |
+| `outputSchema` | `{ "type": "object", "properties": {} }` | **Never populate** — runtime streams events, does not fill output. Exception: inline-in-flow conversational agents, authored under the `uipath-maestro-flow` skill ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-pattern 1). |
 | `messages[1].content` | `""` | **Keep blank** — Conversational Service injects the user turn at runtime ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-pattern 3). |
 | `settings.temperature` | `0` | Raise for open-ended brainstorming or casual chats. Keep `0` for factual support flows. |
 | `settings.maxTokens` | `64000` | Set ≤ the model's `MaxTokens` cap — see [model-selection-guide.md](../model-selection-guide.md#1-discover-primary-path). |
@@ -115,7 +115,7 @@ User message: `""` — left blank. The Conversational Service injects the user t
 - **Vague role** — "You are a helpful agentic assistant." Name the role and bound the scope.
 - **No tool-call criteria** — agent over-calls or under-calls tools.
 - **Long tool-call loops** - agent runtime may stop and require the user to confirm continuation after a single agent run (turn) consists of a series of over 8 steps that each involve tool-call(s). Note that this is not a limitation on total parallel tool-calls on any individual step, so aim to parallelize tool-calls when possible and/or ask for user-confirmation to break up long loops of sequential steps.
-- **Populating `outputSchema`** — runtime streams events; populated schemas never get filled and confuse the agent ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-pattern 1).
+- **Populating `outputSchema`** — runtime streams events; populated schemas never get filled and confuse the agent. Exception: inline-in-flow conversational agents ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-pattern 1).
 - **Templating data into the user message** — the user message content stays blank; per-exchange context goes into the **system prompt** via `inputSchema` templating.
 - **Adding `messages` or `uipath__*` to `inputSchema`** — reserved names; runtime injects ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Anti-patterns 4 and 5).
 - **Using built-in validator guardrails (PII, harmful content, etc.) or `Agent`/`Llm` scopes** — built-in validators are autonomous-only and silently ignored; conversational agents support only Custom deterministic `Tool`-scoped guardrails ([critical-rules/conversational-critical-rules.md](../critical-rules/conversational-critical-rules.md) Critical Rule 1).

package/skills/uipath-automationhub/SKILL.md

@@ -68,5 +68,6 @@ Every addition keeps the skill's three invariants: collect inputs before the fir
 ## Notes
 
 - **Cloud token only** — authorization is the user's real AH permissions; you see and can do exactly what their AH role allows.
+- **If Automation Hub isn't available on the tenant, say so plainly and stop** — never let it surface as a generic failure. Two cases with **different remedies**: *not enabled* (only an admin can fix it) and *reachable but never onboarded* (self-service). Signals, and the exact wording to quote verbatim rather than paraphrase, live in one home per transport: [`references/api-endpoints.md`](references/api-endpoints.md) → **Automation Hub not available on this tenant** for the raw-API flows, [`references/cli-commands.md`](references/cli-commands.md) → same heading for the CLI flows.
 - The publish flow fetches the idea-flow schema live, so it adapts automatically if fields change on the tenant.
 - **Open dependency:** in a hosted runtime (e.g. Process Scribe/Delegate) the cloud token is expected via the environment (Authentication, option 1). Confirm the runtime provides `UIPATH_CLI_AUTH_TOKEN` (or an equivalent) before relying on it in production.

package/skills/uipath-automationhub/references/api-endpoints.md

@@ -138,5 +138,27 @@ Linked components for the process.
 | 400 | Validation — missing required field, invalid enum, empty `user_inputs`, missing `OVERVIEW_NAME` |
 | 401 | Unauthorized — token missing/expired, or `x-ah-openapi-auth` was wrongly sent |
 | 403 | Forbidden — the user lacks the AH permission (authorization = the user's real AH role) |
-| 404 | Wrong URL, or AH not enabled on the tenant |
+| 404 | Wrong URL, or AH not available on the tenant — see **Automation Hub not available on this tenant** below |
 | 409 | Duplicate process name |
+
+### Automation Hub not available on this tenant
+
+Two distinct cases, with **different remedies** — don't collapse them, the advice differs:
+
+**1. AH is not enabled for the tenant.** The tenant has no Automation Hub service at all. Signals: a **404** whose body says `not found in organization`, or a **3xx redirect** to `portal_/unregistered` (following it would surface an HTML portal page as a JSON parse error). The user cannot fix this themselves — report exactly:
+
+> Please contact your administrator to enable Automation Hub on this tenant.
+
+**2. AH is reachable but the tenant was never onboarded into it.** The service answers **422 Tenant Lookup Error** on every call. This one *is* self-service — report exactly:
+
+> Automation Hub is reachable for this tenant but has not finished setup. Open Automation Hub in the browser once to complete it, then retry.
+
+In both cases: **stop after reporting** — do not retry, do not fall back to an admin OpenAPI token, and do not attempt the write against another tenant unless the user asks. Quote the message verbatim; don't paraphrase it.
+
+**Making the signals observable from `curl`.** `curl` reports the status but not *where* a 3xx points, so the first call each flow makes against the tenant asks for both:
+
+```bash
+curl -s -w "\n%{http_code} %{redirect_url}" …
+```
+
+The last line is then `<status> <redirect target>`: `%{redirect_url}` is empty on any non-3xx and carries the resolved `Location` on a 3xx — which is what makes the `portal_/unregistered` case above distinguishable from an ordinary redirect. **Never add `-L`.** Following the redirect throws away the one diagnosable signal and hands you an HTML portal page, which then fails as a JSON parse error — exactly the generic failure this section exists to prevent.

package/skills/uipath-automationhub/references/cli-commands.md

@@ -12,6 +12,17 @@ The CLI wraps the same Open API endpoints as [`api-endpoints.md`](api-endpoints.
 
 If a command fails with an authentication error, tell the user to run `uip login` — never ask for or handle a raw token yourself.
 
+## Automation Hub not available on this tenant
+
+The CLI already classifies this for you — read its `Instructions` field:
+
+- `Instructions` mentioning **"not provisioned on this tenant"** → AH is not enabled. Report: *"Please contact your administrator to enable Automation Hub on this tenant."*
+- `Instructions` mentioning **"no tenant record of its own yet"** → reachable but not onboarded. Report: *"Automation Hub is reachable for this tenant but has not finished setup. Open Automation Hub in the browser once to complete it, then retry."*
+
+Either way **stop** — don't retry and don't try another tenant unless asked, and quote the message verbatim rather than paraphrasing it.
+
+> This section is the **canonical wording for the CLI path**; the CLI flows reference it instead of restating it, so each message exists in exactly one place per transport (raw-API twin: [`api-endpoints.md`](api-endpoints.md) → **Automation Hub not available on this tenant**, which also carries the raw signals behind each case). The two homes exist because the CLI files stay self-contained for the day the raw-API fallback retires — keep them in sync if the wording ever changes.
+
 ## Output envelope (every command)
 
 Always pass `--output json`. Success:

package/skills/uipath-automationhub/references/get-process-cli-guide.md

@@ -19,6 +19,8 @@ Fetches one process (by id or search) and its documents, and downloads document
 uip ah automations get $PROCESS_ID --output json
 ```
 
+If the command fails with `Instructions` about AH **not being provisioned** on the tenant, or about the tenant having **no AH record yet**, report the message for the matching case, verbatim, from [`cli-commands.md`](cli-commands.md) → **Automation Hub not available on this tenant**, and stop.
+
 `Data` is the projected record (`Id`, `Name`, `Phase`, `PhaseStatus`, `Tags`, …). Add `--all-fields` only when you need the raw record (e.g. `process_slug` for the deep link). `Failure` with not-found → no such process; auth error → `uip login`.
 
 ## Step 3: Fetch the documents

package/skills/uipath-automationhub/references/get-process.md

@@ -9,19 +9,22 @@ Fetches one process (by id or search) and its documents from Automation Hub, aut
 - If the caller gives a **process id**, use it directly.
 - Otherwise search by name:
   ```bash
-  curl -s -H "Authorization: Bearer $ACCESS_TOKEN" \
+  curl -s -w "\n%{http_code} %{redirect_url}" -H "Authorization: Bearer $ACCESS_TOKEN" \
     "$BASE_URL/$ORG/$TENANT/automationhub_/api/v1/openapi/automations?search=$QUERY&limit=20"
   ```
-  If one clear match → use its `process_id`. If several → show a short list (name + id + owner) and ask the user to pick. If none → tell the user and stop.
+  The last line is `<status> <redirect target>` (empty target unless 3xx). Check it **before** the results: a **404 / 3xx to `portal_/unregistered` / 422 tenant lookup** means AH isn't available on this tenant at all — handle it as in Step 2, don't report it as "no match". Never add `-L`.
+
+  On a 200: one clear match → use its `process_id`. If several → show a short list (name + id + owner) and ask the user to pick. If none → tell the user and stop.
 
 ## Step 2: Fetch the process
 
 ```bash
-curl -s -w "\n%{http_code}" -H "Authorization: Bearer $ACCESS_TOKEN" \
+curl -s -w "\n%{http_code} %{redirect_url}" -H "Authorization: Bearer $ACCESS_TOKEN" \
   "$BASE_URL/$ORG/$TENANT/automationhub_/api/v1/openapi/automations/$PROCESS_ID"
 ```
+The last line is `<status> <redirect target>` (empty target unless 3xx) — the target is what separates a `portal_/unregistered` redirect from any other 3xx. Never add `-L`.
 - **200** → keep the record; project to the useful fields for display (name, status/phase, category, owner, description). The raw record is large — don't dump it all unless asked.
-- **401** → re-authenticate. **403** → the user can't view this process. **404** → no such process.
+- **401** → re-authenticate. **403** → the user can't view this process. **404** → no such process — *unless* the body says `not found in organization` (or the call 3xx-redirects to `portal_/unregistered`, or answers **422 tenant lookup**), which means AH itself is not available on this tenant: report the message for the matching case, verbatim, from [`api-endpoints.md`](api-endpoints.md) → **Automation Hub not available on this tenant**, and stop.
 
 ## Step 3: Fetch the documents
 

package/skills/uipath-automationhub/references/publish-process-cli-guide.md

@@ -12,7 +12,7 @@ uip ah idea-flows list --output json
 
 - `Result: Success` → keep `Data` (flow names + ids) and tell the user "Connected to Automation Hub."
 - Auth failure → tell the user to run `uip login` (or, in Delegate, to sign in). Never ask for a raw token.
-- `Failure` mentioning the tenant/enablement → AH is not enabled on this tenant; stop.
+- `Failure` mentioning the tenant/enablement → AH is not available on this tenant. Report the message for the matching case, verbatim, from [`cli-commands.md`](cli-commands.md) → **Automation Hub not available on this tenant** — then **stop**; nothing later in this flow can succeed.
 
 ## Step 2: Pick the idea flow
 

package/skills/uipath-automationhub/references/publish-process.md

@@ -9,15 +9,17 @@ Creates one process in Automation Hub from a schema-driven payload and attaches
 Verify the resolved token with a cheap call — this also fetches the idea flows you need next:
 
 ```bash
-curl -s -w "\n%{http_code}" \
+curl -s -w "\n%{http_code} %{redirect_url}" \
   -H "Authorization: Bearer $ACCESS_TOKEN" \
   "$BASE_URL/$ORG/$TENANT/automationhub_/api/v1/openapi/idea-flows"
 ```
 
+The last line is `<status> <redirect target>` — the target is empty unless the response was a 3xx. Read both: a 3xx alone is ambiguous, a 3xx **to `portal_/unregistered`** is the tenant-not-enabled signal below. Never add `-L`.
+
 - **200** → save the `data` array (reused in Step 2) and tell the user "Connected to Automation Hub."
 - **401** → token missing/expired: if it came from `~/.uipath/.auth`, ask the user to run `uip login` again; re-resolve and retry. **Never** add `x-ah-openapi-auth` to "fix" a 401 — that routes to the admin-token path and guarantees failure.
 - **403** → the user is authenticated but lacks AH access on this tenant.
-- **404 / network** → wrong URL or AH not enabled; confirm the org/tenant.
+- **404 / 3xx to `portal_/unregistered` / 422 tenant lookup** → AH is not available on this tenant. Confirm the org/tenant first; if they're right, report the message for the matching case, verbatim, from [`api-endpoints.md`](api-endpoints.md) → **Automation Hub not available on this tenant** — then **stop**.
 
 Do not proceed until you have a 200.
 

package/skills/uipath-maestro-flow/references/author/plugins/conversational-agent/impl.md

@@ -206,7 +206,7 @@ Reads recent exchanges without waiting. Rarely needed, and constrained — see [
 
 ## Structured Outputs
 
-In addition to responding to the chat, an **inline** conversational agent can also return named fields for a downstream node to route on. Published and in-solution agents cannot.
+In addition to responding to the chat, an **inline** conversational agent can also return named fields for a downstream node to route on. Imported standalone conversational agents (published or in-solution) do not support structured output fields.
 
 Declare each field in two places or it yields nothing at run time:
 
@@ -217,6 +217,24 @@ Declare each field in two places or it yields nothing at run time:
 
 Bind it downstream as `$vars.<agentNodeId>.output.shouldHandoff`. Writing one side without the other passes `agent validate` and `flow validate` — nothing checks the pair.
 
+### Prompting: what goes where
+
+The prompts that drive the agent's chat replies and structured output differ:
+
+| Generated | Driven by |
+| --- | --- |
+| the chat reply | the system prompt **only** |
+| the structured outputs | the system prompt **plus** each field's `description` |
+
+So split the instructions by destination — *what to say* and *response instructions* in the system prompt, *how to fill the field* in that field's `description` (write the same description in both `agentOutputVariables[]` and `outputSchema.properties`):
+
+| Where | Example |
+| --- | --- |
+| system prompt | "Thank the user when they would like to end the conversation." |
+| `endConversation` (boolean) `description` | "Set to true when the user intends to end the conversation." |
+
+**Do not name the output field and how to set it in the system prompt.** An instruction like "set `endConversation` to `true` when the user says goodbye" in the system prompt may make the LLM emit the structured value to the chat or look for a tool to set the output variables.
+
 ## Wire the Edges
 
 An **inline** agent leaves on `success`; an in-solution or published one leaves on `output`. The smallest loop:

package/skills/uipath-maestro-flow/references/author/plugins/conversational-agent/planning.md

@@ -129,5 +129,5 @@ In the architectural plan:
 - `chat-agent: <description>` — one line per agent; omit for a scripted chat. Inline: Reuse the [inline-agent](../inline-agent/planning.md) annotations. In-solution or published: `<agent-name> in <folder-path>`.
 - `chat-agent-flavor: <agent-name> = inline | in-solution | published` — one per agent above; decides the node type (`uipath.agent.conversational` for inline, `uipath.core.agent.*` for the others — see the [flavor table](#pick-the-agent-flavor-before-you-build) for which suffix each takes) and on which port (`success` for inline, `output` for the others)
 - `chat-send-message: <purpose>` — one line per flow-authored message (loading messages, handoff notice, node output results); a scripted chat consists mostly of these
-- `chat-structured-output: <agent-name> = <fieldName>` — only when the flow branches on that conversational agent's reply; forces that conversational agent to inline flavor because in-solution and published conversational agents have no structured outputs
+- `chat-structured-output: <agent-name> = <fieldName>` — only when the flow branches on that conversational agent's reply; forces that conversational agent to inline flavor because in-solution and published conversational agents have no structured outputs.
 - Tools, contexts, and escalations on any inline chat agent reuse the [inline-agent](../inline-agent/planning.md) annotations

package/version-manifest.json

@@ -1,5 +1,5 @@
 {
   "schemaVersion": 2,
-  "skillsVersion": "1.202.0-preview.755",
+  "skillsVersion": "1.202.0-preview.767",
   "targetCli": "^1.202.0"
 }